Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1ac591146ceadd98cb889edc410e5ce5a15484b942ad2db9471bc717160fff4
+oid sha256:bafc42beb37f45eb961f6515d020b6884378d6c6097aa99cc4b01e8caeaf7438
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:975655fb1c36d98b62229d251b381cb5e32b2a3a4c6ddc296253123b0f42677d
+oid sha256:3c3d311eddddc39d90d2a1893000c93df6f120a257e8bf7bff3b2fca1dc2e5a7
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b14d0c915e2c4063f110f3dbec036a026b529b8820509b2913f154771be18b
+oid sha256:e9ed9626ba6e412f40126198b85320c11d70caab3bee87c19069e3aea6dd4f83
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00032792709087679507,
+  "epoch": 0.0004918906363151926,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 18.026,
       "eval_steps_per_second": 9.013,
       "step": 6
+    },
+    {
+      "epoch": 0.0003825816060229276,
+      "grad_norm": 1.4767484664916992,
+      "learning_rate": 0.00014,
+      "loss": 2.1604,
+      "step": 7
+    },
+    {
+      "epoch": 0.00043723612116906006,
+      "grad_norm": 1.1799358129501343,
+      "learning_rate": 0.00016,
+      "loss": 1.9058,
+      "step": 8
+    },
+    {
+      "epoch": 0.0004918906363151926,
+      "grad_norm": 1.1987409591674805,
+      "learning_rate": 0.00018,
+      "loss": 2.057,
+      "step": 9
+    },
+    {
+      "epoch": 0.0004918906363151926,
+      "eval_loss": 1.8708151578903198,
+      "eval_runtime": 427.3376,
+      "eval_samples_per_second": 18.028,
+      "eval_steps_per_second": 9.014,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2219477097775104.0,
+  "total_flos": 3329215646662656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null